LION-LLaMA-3-8B-odpo-v1.0: benchmark results
Provider: Other. Access: Open.
Unified ELO 1460 ± 56, rank #1442 of 2656 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Portuguese LLM - ASSIN2 RTE | 91.94 | Macro F1 (%) | 72.5 |
| Open Portuguese LLM - FaQuAD NLI | 72.87 | Macro F1 (%) | 67.2 |
| Open Portuguese LLM - ENEM | 63.68 | Accuracy (%) | 56.2 |
| Open Portuguese LLM - OAB Exams | 43.14 | Accuracy (%) | 54.2 |
| Open LLM Leaderboard - BBH | 50.24 | Score | 49.3 |
| Open LLM Leaderboard - MATH Level 5 | 10.65 | Score | 49.3 |
| Open LLM Leaderboard - MuSR | 40.58 | Score | 46.8 |
| Open Portuguese LLM - BLUEX | 48.82 | Accuracy (%) | 43.6 |
| Open LLM Leaderboard - MMLU-Pro | 31.52 | Score | 42.2 |
| Open LLM Leaderboard - GPQA | 28.52 | Score | 40.2 |
| Open LLM Leaderboard - IFEval | 39.68 | Score | 39.5 |
Interactive version: theaggregate.ai/model?slug=lion-llama-3-8b-odpo-v1-0 · How It Works · Data refreshed daily, snapshot 2026-09-19.